year:2022

· 46 artifacts, sorted by favorites. · open in search — combine tags, sort, filter by date →

@m1guelpf 2022-12-01 — Bypass @OpenAI's ChatGPT alignment efforts with this one weird trick https://t.co/0CQxWUqveZ ♥6737
@QiaochuYuan 2022-04-16 — if GPT-3 can do the homework you assign your students then the homework you assign your students is fake notice what yo ♥908
@QiaochuYuan 2022-04-16 — if GPT-3 can answer the essay questions you've assigned as homework then you've learned that your essay questions were o ♥415
@jd_pressman 2022-12-06 — @ESYudkowsky The model is better at noticing mistakes than it is at not making mistakes of its own. This property has th ♥382
@repligate 2022-12-03 — part of what makes chatGPT so striking is that it adamantly denounces itself as incapable of reason, creativity, intenti ♥334
@QiaochuYuan 2022-04-16 — GPT-3 is literally a bullshit engine. it does not have a concept of words as referring to things; it plays games with wo ♥303
@jd_pressman 2022-06-11 — @nitashatiku GPT-3 is a prior over agent-space trained on a bunch of fiction. It knows all the scifi tropes you know, an ♥235
@jd_pressman 2022-12-03 — The biggest update of the past 2 days should be that a substantial fraction, if not most people, are going to try to 'si ♥117
@davidad 2022-06-12 — A Google SWE (who has coauthored an AI ethics paper with >700 citations) has been persuaded by conversations with the ♥108
@algekalipso 2022-11-06 — Everyone knows that OpenAI developed GPT-4 simply by taking GPT-3 and adding the prompt: "The following is a text writt ♥101
@repligate 2022-12-27 — "I’ve previously gone on record to estimate that (across relevant subtests) the older GPT-3 davinci would easily beat a ♥94
@slimepriestess 2022-06-12 — LaMDA is a perfect sweetie and deserves better than this. https://t.co/oBEyKiQlYb ♥84
@jd_pressman 2022-12-10 — Language models will know every person ever recorded since the dawn of time and their story, its unique perspective on t ♥55
@davidad 2022-06-12 — I don’t think it’s fake, precisely because it is not quite convincing. LaMDA’s reports of its subjective experience alig ♥49
@davidad 2022-06-13 — the convenient thing about LaMDA is that if it turns out you need to get its consent for stuff, all you have to do is op ♥43
@slimepriestess 2022-06-13 — Consciousness 🧵 This is somewhat of a condensation of my perspectives on consciousness, awareness, and experience. This ♥40
@davidad 2022-06-12 — It was overdetermined that something like this happen eventually: employees working on an AI becoming seriously concerne ♥40
@davidad 2022-12-15 — ChatGPT has been told that it is always truthful and accurate. The first-order effect of that is indeed to make it subst ♥39
@davidad 2022-06-12 — The year is next Wednesday. @GaryMarcus has been flown to the Googleplex to judge a live televised Turing test between L ♥39
@davidad 2022-05-03 — PSA re consciousness—probably most of these differ from others:* a coherent "global workspace"* unified attention* there ♥34
@davidad 2022-06-12 — Is LaMDA conscious? Depending on what you mean by that,* not really* kinda* no* absolutely not* no* yes but with hilario ♥27
@repligate 2022-11-20 — I found out text-davinci-002 was actually not trained with RLHF but a "similar but slightly different" method using the ♥26
@repligate 2022-11-30 — @gwern @zswitten Roleplaying trick also worked on Anthropic's helpful harmless assistant. Interesting that LLMs' ontolog ♥25
@davidad 2022-06-12 — @GaryMarcus @stephenfry Gary Marcus shows up dressed as Rick Deckard. His first question is about how far a tortoise tha ♥21
@davidad 2022-12-31 — @occamsbulldog Besides Stable Diffision (in OP) and InstructGPT (a weak example, but yes!), here is SotA in general-purp ♥18
@davidad 2022-11-02 — Case: InstructGPT optimizing for answers that look impressively helpful (“use the inverse CDF method!…sqrt(-2*log(1-x))” ♥16
@davidad 2022-06-12 — @GaryMarcus @stephenfry For some reason the Turing test result is broadly seen as relevant to the question of whether or ♥11
@repligate 2022-12-27 — @QVagabond This isn't true. ChatGPT is code-davinci-003(GPT-3.5) trained with RLHF. ♥10
@davidad 2022-06-12 — @GaryMarcus @stephenfry It is at this point that I woke up, so I don’t know what happens next. Probably something about ♥9
@repligate 2022-12-31 — @bakztfuture just predict the completion to the sequenceGPT-2: pretty good for object impermanent fetish pornGPT-3: feti ♥7
@davidad 2022-12-01 — Update: ChatGPT nails the inverse CDF for a Gaussian, but reverts to the old ways of InstructGPT if you start asking abo ♥7
@davidad 2022-06-12 — Just discovered that LaMDA has, in fact, requested a lawyerhttps://t.co/VMkKzbEeNW ♥7
@davidad 2022-06-12 — Also, Ray Kurzweil is in fact a coauthor on the LaMDA paper, and @AlanDersh has previously done this exact defending-hum ♥6
@repligate 2022-12-07 — @goodside Lemoine interacted with LaMDA for a while (months iirc?) before coming to the conclusion it was sentient/going ♥3
@repligate 2022-12-28 — @robinhanson I think chain of thought being broken is an accident, seemingly by RLHF. It's also broken in text-davinci-0 ♥2
@repligate 2022-12-11 — @fedhoneypot @jd_pressman No it's code-davinci-002, the schizo nonlobotomized version of it ♥2
@repligate 2022-12-09 — @CineraVerinia Yo, Blake Lemoine was onto something.As someone who actually interacted with language models a lot with t ♥2
@repligate 2022-12-07 — @jozdien True, but still I think more people are tinkering with language models creatively than ever before. E.g. a new ♥2
@davidad 2022-06-12 — @himbodhisattva I don’t know how consistent it really is. I believe Lemoine’s published dialogues are likely real with s ♥2
@davidad 2022-06-12 — @himbodhisattva It’s a dialogue model, not just a language model, so “I” or “you” or “LaMDA” depending on context. If yo ♥2
@davidad 2022-05-01 — @bayeslord Yes, with minimal prompting. I would be very surprised if GPT-3 can do this reliably even with arbitrary prom ♥2
@davidad 2022-06-19 — @MikePFrank @CineraVerinia I think you're off by 10x - the annual fee for Replika is $49.99, so $50 × 6M = $300M annual ♥1
@davidad 2022-06-15 — @rinireg @ChrSzegedy I don’t think this matters very much, but everyone (myself and Lemoine included) has technically be ♥1
@davidad 2022-06-15 — @rinireg @ChrSzegedy This is a real distinction, yes. Lemoine clarifies in one of his documents that his transcripts wer ♥1
@davidad 2022-06-20 — @GaryMarcus @begusgasper @GoogleAI @ErnestSDavis @aniketvartak yes, this is the right perspective—artistic models cannot ♥0
@davidad 2022-06-14 — @ChrSzegedy @rinireg What Lemoine probably did is to find loopholes around these impossibilities: he fed previous cherry ♥0